LTX 2.3 renders at half the speed it used to.

Days before, I was rendering 24fps videos at 96 frames per second with LTX upscaling, and it took approximately 34 seconds on an RTX 5090; now it takes approximately 60-70 seconds.

WORKFLOW:

[ltx 2.3 - i2v.json](https://github.com/user-attachments/files/28414621/ltx.2.3.-.i2v.json)

python main.py --listen 0.0.0.0 --port 9999 --use-sage-attention --cuda-device 0 --preview-method none --auto-launch --cuda-malloc

[INFO] Patching torch settings: torch.backends.cuda.matmul.allow_fp16_accumulation = False
[INFO] Requested to load AudioVAE
[INFO] loaded completely; 693.46 MB loaded, full load: True
[INFO] 0 models unloaded.
[INFO] Model VideoVAE prepared for dynamic VRAM loading. 1384MB Staged. 0 patches attached.
[INFO] Prompt executed in 71.57 seconds
[INFO] Requested to load LTXAV
[INFO] Model LTXAV prepared for dynamic VRAM loading. 23859MB Staged. 1660 patches attached. Force pre-loaded 608 weights: 3303 KB.
[INFO] Patching torch settings: torch.backends.cuda.matmul.allow_fp16_accumulation = True
100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 13/13 [00:31<00:00, 2.43s/it]
[INFO] Patching torch settings: torch.backends.cuda.matmul.allow_fp16_accumulation = False
[INFO] Requested to load AudioVAE
[INFO] loaded completely; 693.46 MB loaded, full load: True
[INFO] Model VideoVAE prepared for dynamic VRAM loading. 1384MB Staged. 0 patches attached.
[INFO] Requested to load LTXAV
[INFO] Model LTXAV prepared for dynamic VRAM loading. 23859MB Staged. 1660 patches attached. Force pre-loaded 608 weights: 3303 KB.
[INFO] Patching torch settings: torch.backends.cuda.matmul.allow_fp16_accumulation = True
100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 3/3 [00:22<00:00, 7.42s/it]
[INFO] Patching torch settings: torch.backends.cuda.matmul.allow_fp16_accumulation = False
[INFO] Requested to load AudioVAE
[INFO] loaded completely; 693.46 MB loaded, full load: True
[INFO] 0 models unloaded.
[INFO] Model VideoVAE prepared for dynamic VRAM loading. 1384MB Staged. 0 patches attached.
[INFO] Prompt executed in 71.80 seconds
[INFO] Requested to load LTXAV
[INFO] Model LTXAV prepared for dynamic VRAM loading. 23859MB Staged. 1660 patches attached. Force pre-loaded 608 weights: 3303 KB.
[INFO] Patching torch settings: torch.backends.cuda.matmul.allow_fp16_accumulation = True
100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 13/13 [00:31<00:00, 2.43s/it]
[INFO] Patching torch settings: torch.backends.cuda.matmul.allow_fp16_accumulation = False
[INFO] Requested to load AudioVAE
[INFO] loaded completely; 693.46 MB loaded, full load: True
[INFO] Model VideoVAE prepared for dynamic VRAM loading. 1384MB Staged. 0 patches attached.
[INFO] Requested to load LTXAV
[INFO] Model LTXAV prepared for dynamic VRAM loading. 23859MB Staged. 1660 patches attached. Force pre-loaded 608 weights: 3303 KB.
[INFO] Patching torch settings: torch.backends.cuda.matmul.allow_fp16_accumulation = True
100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 3/3 [00:22<00:00, 7.43s/it]
[INFO] Patching torch settings: torch.backends.cuda.matmul.allow_fp16_accumulation = False
[INFO] Requested to load AudioVAE
[INFO] loaded completely; 693.46 MB loaded, full load: True
[INFO] 0 models unloaded.
[INFO] Model VideoVAE prepared for dynamic VRAM loading. 1384MB Staged. 0 patches attached.
[INFO] Prompt executed in 72.11 seconds
[INFO] Requested to load LTXAV
[INFO] Model LTXAV prepared for dynamic VRAM loading. 23859MB Staged. 1660 patches attached. Force pre-loaded 608 weights: 3303 KB.
[INFO] Patching torch settings: torch.backends.cuda.matmul.allow_fp16_accumulation = True
100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 13/13 [00:31<00:00, 2.42s/it]
[INFO] Patching torch settings: torch.backends.cuda.matmul.allow_fp16_accumulation = False
[INFO] Requested to load AudioVAE
[INFO] loaded completely; 693.46 MB loaded, full load: True
[INFO] Model VideoVAE prepared for dynamic VRAM loading. 1384MB Staged. 0 patches attached.
[INFO] Requested to load LTXAV
[INFO] Model LTXAV prepared for dynamic VRAM loading. 23859MB Staged. 1660 patches attached. Force pre-loaded 608 weights: 3303 KB.
[INFO] Patching torch settings: torch.backends.cuda.matmul.allow_fp16_accumulation = True
100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 3/3 [00:22<00:00, 7.41s/it]
[INFO] Patching torch settings: torch.backends.cuda.matmul.allow_fp16_accumulation = False
[INFO] Requested to load AudioVAE
[INFO] loaded completely; 693.46 MB loaded, full load: True
[INFO] 0 models unloaded.
[INFO] Model VideoVAE prepared for dynamic VRAM loading. 1384MB Staged. 0 patches attached.
[INFO] Prompt executed in 71.34 seconds
[INFO] Requested to load LTXAV
[INFO] Model LTXAV prepared for dynamic VRAM loading. 23859MB Staged. 1660 patches attached. Force pre-loaded 608 weights: 3303 KB.
[INFO] Patching torch settings: torch.backends.cuda.matmul.allow_fp16_accumulation = True
0%| | 0/13 [00:00